Skip to main content
Collect candidate citation-share and rank changes for follow-up. MCP tool: get_significant_findings. Operation: read. Uses the authorized connection; no project or content changes are made by this tool.

Parameters

Example call

Replace ID placeholders and example selections with values from your account. This is the params object for MCP tools/call.

Read the response

Read data.findings, data.reference_run_id, and data.reference_type. Up to 50 findings include kind, subject, contrast, scope, and correction metadata. correction.method is none in this edition and family_size records the comparison family.

Fields to use

These selected fields explain the example and the result to preserve. Field presence depends on the response; this is not a complete response schema.

Response example

Selected fields from an observed IQRush Dev response. Lists are shortened and project/run IDs are placeholders. Omitted fields remain available in the actual response.
Read the actual returned scope, counts, and interval levels before interpreting these fields.

Important behavior

These are exploratory candidates, not a set of confirmed changes. Broad screening increases chance findings. Use a specific follow-up question and retain the comparison limitations. Check tool and payload errors before using the result. Response handling explains estimates and empty results; errors and recovery covers invalid requests and temporary failures. HTTP equivalent: Find changes to investigate. HTTP parameters and defaults can differ.